Unverified50% confidenceBenchmarkExact time
On the same machine and model, the decoding speed difference between low power mode and high power mode is 1.4 to 3.8 times; for example, running Qwen 3.5 35B on Ollama gives 51.9 tokens/s in low power and 107.1 tokens/s in high power.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
UnverifiedWhen running Qwen3-Next-Flash (Autoround W4A16 quantization), the prefill speed was approximately 1.3k tokens/s, and the generation speed reached 70 tokens/s (code) / 60 tokens/s (prose), with support for 128k+ long context.75% similarUnverified3B 模型在现代 CPU 上通过 llama.cpp 推理速度通常达到 10-30 tokens/秒74% similarUnverifieddecode阶段的生成速度近似等于内存带宽÷模型大小，例如在内存带宽273GB/s的M4 Pro上运行4GB的Q4量化7B模型理论最大生成速度约68 tokens/s72% similarUnverifiedllama.cpp通过纯CPU推理和4-bit GGUF量化格式，使7B参数模型在无GPU的普通服务器上达到每秒20-40 tokens的生成速度72% similarUnverifiedEven if a small portion of the model overflows into system memory, speed drops dramatically; experiments show the same small model runs at 151 tokens/s in RTX 5090 VRAM but only 8 tokens/s when placed in system memory.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1015146API
curl https://kongchang.com/api/v1/knowledge/claims/1015146MCP
get_claim(id=1015146)